Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    each group

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     의
    0.80
    ক্ষণের
    0.78
     재미
    0.76
     멋
    0.75
    모
    0.74
     패
    0.74
     buenas
    0.74
     창
    0.73
    ļu
    0.73
     q
    0.73
    POSITIVE LOGITS
     insulted
    0.89
     gruppo
    0.88
    انہوں
    0.84
     Gruppe
    0.84
    ><?
    0.80
     beiden
    0.80
     filas
    0.79
    älfte
    0.78
     grupo
    0.78
    Grouping
    0.78
    Act Density 0.276%

    No Known Activations